├── .gemini └── config.yaml ├── .github ├── CODEOWNERS ├── PULL_REQUEST_TEMPLATE.md ├── dependabot.yml └── workflows │ ├── .deprecate │ ├── e2e_ppo_trainer.yml │ ├── e2e_ppo_trainer_megatron_sglang.yml │ └── e2e_prime.yml │ ├── README.md │ ├── check-pr-title.yml │ ├── checkpoint_converter.yml │ ├── cpu_unit_tests.yml │ ├── doc.yml │ ├── e2e_ascend.yml │ ├── e2e_dapo.yml │ ├── e2e_eval_aime24.yml │ ├── e2e_genrm_remote.yml │ ├── e2e_one_step_off_policy.yml │ ├── e2e_ppo_trainer.yml │ ├── e2e_ppo_trainer_megatron_sglang.yml │ ├── e2e_ppo_trainer_megatron_vllm.yml │ ├── e2e_sft.yml │ ├── e2e_spin.yml │ ├── e2e_sppo.yml │ ├── gpu_unit_tests.yml │ ├── model.yml │ ├── pre-commit-full.yml │ ├── pre-commit.yml │ ├── sanity.yml │ ├── scorecard.yml │ ├── secrets_scan.yml │ ├── sgl.yml │ ├── type-coverage-check.yml │ └── vllm.yml ├── .gitignore ├── .pre-commit-config.yaml ├── .readthedocs.yaml ├── README.md ├── add_api_instruction_baseline_sglang.sh ├── add_trained_instruction_baseline_sglang.sh ├── analyze_baseline_results_f1_macro.py ├── api_instruction_helper.py ├── baseline_eval_v3_modular.py ├── docs ├── Makefile ├── README.md ├── README_vllm0.7.md ├── README_vllm0.8.md ├── _static │ ├── custom.css │ ├── js │ │ ├── resizable-sidebar.js │ │ └── runllm-widget.js │ └── logo.png ├── advance │ ├── agent_loop.rst │ ├── checkpoint.rst │ ├── dpo_extension.rst │ ├── fsdp_extension.rst │ ├── megatron_extension.rst │ ├── one_step_off.md │ ├── placement.rst │ ├── ppo_lora.rst │ ├── rollout_skip.rst │ ├── rollout_trace.rst │ └── rope.rst ├── algo │ ├── baseline.md │ ├── dapo.md │ ├── entropy.md │ ├── gpg.md │ ├── grpo.md │ ├── opo.md │ ├── ppo.md │ ├── spin.md │ └── sppo.md ├── amd_tutorial │ ├── amd_build_dockerfile_page.rst │ └── amd_vllm_page.rst ├── api │ ├── data.rst │ ├── single_controller.rst │ ├── trainer.rst │ └── utils.rst ├── ascend_tutorial │ ├── ascend_profiling.rst │ ├── ascend_profiling_en.rst │ └── ascend_quick_start.rst ├── conf.py ├── examples │ ├── config.rst │ ├── gsm8k_example.rst │ ├── multi_modal_example.rst │ ├── ppo_code_architecture.rst │ └── sandbox_fusion_example.rst ├── faq │ └── faq.rst ├── hybrid_flow.rst ├── index.rst ├── perf │ ├── device_tuning.rst │ ├── dpsk.md │ ├── nsight_profiling.md │ └── perf_tuning.rst ├── preparation │ ├── prepare_data.rst │ └── reward_function.rst ├── requirements-docs.txt ├── sglang_multiturn │ ├── interaction_system.rst │ ├── multiturn.rst │ ├── sandbox_fusion.rst │ └── search_tool_example.rst ├── single_controller.rst ├── start │ ├── agentic_rl.rst │ ├── install.rst │ ├── more_resources.rst │ ├── multinode.rst │ ├── quickstart.rst │ └── ray_debug_tutorial.rst └── workers │ ├── fsdp_workers.rst │ ├── megatron_workers.rst │ ├── ray_trainer.rst │ └── sglang_worker.rst ├── env.yml ├── examples ├── data_preprocess │ ├── aime2024_multiturn_w_tool.py │ ├── dapo_multiturn_w_tool.py │ ├── full_hh_rlhf.py │ ├── geo3k.py │ ├── geo3k_multiturn_w_tool.py │ ├── gsm8k.py │ ├── gsm8k_multiturn_w_interaction.py │ ├── gsm8k_multiturn_w_tool.py │ ├── gsm8k_tool_agent_loop.py │ ├── hellaswag.py │ ├── math_dataset.py │ ├── multiturn.py │ ├── preprocess_search_r1_dataset.py │ └── prompt_gen_v8.py ├── generation │ ├── run_deepseek7b_mutli_node.sh │ └── run_deepseek_v2_lite_math.sh ├── gmpo_trainer │ ├── README.md │ ├── run_qwen2_5-7b_math.sh │ ├── test_dapo_7b_math.sh │ └── test_dapo_qwen3_30b_math.sh ├── gpg_trainer │ ├── gpg.md │ ├── run_qwen2-7b_math.sh │ └── run_qwen2-7b_math_megatron.sh ├── grpo_trainer │ ├── README.md │ ├── run_deepseek671b_math_megatron.sh │ ├── run_deepseek7b_llm.sh │ ├── run_deepseek7b_llm_math.sh │ ├── run_deepseek7b_llm_math_megatron.sh │ ├── run_deepseek7b_llm_seq_balance.sh │ ├── run_minicpmo2_6.sh │ ├── run_moonlight16b_math_megatron.sh │ ├── run_qwen2-7b.sh │ ├── run_qwen2-7b_math.sh │ ├── run_qwen2-7b_math_megatron.sh │ ├── run_qwen2-7b_seq_balance.sh │ ├── run_qwen2-7b_seq_balance_math_megatron.sh │ ├── run_qwen2-7b_sgl_megatron.sh │ ├── run_qwen2_5-3b_gsm8k_grpo_lora.sh │ ├── run_qwen2_5-7b_math_megatron_diff_tp.sh │ ├── run_qwen2_5_32b_grpo_npu.sh │ ├── run_qwen2_5_7b_grpo_discrete_prof_npu.sh │ ├── run_qwen2_5_7b_grpo_e2e_prof_npu.sh │ ├── run_qwen2_5_7b_grpo_npu.sh │ ├── run_qwen2_5_vl-7b-megatron.sh │ ├── run_qwen2_5_vl-7b.sh │ ├── run_qwen2_5_vl-7b_lora.sh │ ├── run_qwen2_5_vl-7b_seq_balance.sh │ ├── run_qwen2_5_vl_32b_npu.sh │ ├── run_qwen2_5_vl_3b_npu.sh │ ├── run_qwen2_5_vl_7b_npu.sh │ ├── run_qwen3-236b_megatron.sh │ ├── run_qwen3-8b.sh │ └── run_qwen3moe-30b_megatron.sh ├── ppo_trainer │ ├── README.md │ ├── run_deepseek7b_llm.sh │ ├── run_deepseek7b_llm_modelscope.sh │ ├── run_deepseek7b_llm_pfppo.sh │ ├── run_deepseek7b_llm_sandbox_fusion.sh │ ├── run_deepseek7b_llm_sp2.sh │ ├── run_deepseek_full_hh_rlhf.sh │ ├── run_deepseek_math_gsm8k_megatron.sh │ ├── run_deepseek_math_gsm8k_megatron_nsys.sh │ ├── run_gemma.sh │ ├── run_moonlight16b_a3b_gsm8k_megatron.sh │ ├── run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh │ ├── run_qwen2-7b_math_gsm8k_megatron.sh │ ├── run_qwen2-7b_rm.sh │ ├── run_qwen2-7b_rm_seq_balance.sh │ ├── run_qwen2-7b_rm_seq_balance_fused_kernels.sh │ ├── run_qwen2-7b_rm_seq_balance_nsys.sh │ ├── run_qwen2-7b_seq_balance.sh │ ├── run_qwen2-7b_sglang_seq_balance.sh │ └── run_qwen2.5-32b.sh ├── ray │ └── tutorial.ipynb ├── reinforce_plus_plus_trainer │ ├── run_qwen2-7b_math_rf.sh │ └── run_qwen2-7b_math_rf_baseline.sh ├── remax_trainer │ ├── run_qwen2.5-3b_seq_balance.sh │ └── run_qwen2.5-7b_seq_balance.sh ├── rloo_trainer │ └── run_qwen2-7b.sh ├── sft │ ├── gsm8k │ │ ├── run_deepseek_6b7.sh │ │ ├── run_gemma_2b.sh │ │ ├── run_gemma_7b.sh │ │ ├── run_qwen2_5_05b_sft_peft_sp2_npu.sh │ │ ├── run_qwen_05_peft.sh │ │ ├── run_qwen_05_sp2.sh │ │ └── run_qwen_05_sp2_liger.sh │ └── multiturn │ │ └── run_qwen_05_sp2.sh ├── sglang_multiturn │ ├── README.md │ ├── config │ │ ├── geo3k_multiturn_grpo.yaml │ │ ├── geo3k_multiturn_megatron_grpo.yaml │ │ ├── gsm8k_multiturn_grpo.yaml │ │ ├── gsm8k_multiturn_grpo_w_interaction.yaml │ │ ├── gsm8k_multiturn_megatron_grpo.yaml │ │ ├── interaction_config │ │ │ └── gsm8k_interaction_config.yaml │ │ ├── retool_multiturn_grpo.yaml │ │ ├── search_multiturn_grpo.yaml │ │ └── tool_config │ │ │ ├── geo3k_tool_config.yaml │ │ │ ├── gsm8k_tool_config.yaml │ │ │ ├── mcp_server.json │ │ │ ├── mcp_tool_config.yaml │ │ │ ├── sandbox_fusion_tool_config.yaml │ │ │ └── search_tool_config.yaml │ ├── geo3k │ │ ├── run_qwen2.5-3b_geo3k_multiturn.sh │ │ ├── run_qwen2.5-3b_geo3k_multiturn_4xgpu.sh │ │ └── run_qwen2.5-3b_megatron_geo3k_multiturn.sh │ ├── run_qwen0.5b_gsm8k_multiturn_curriculum.sh │ ├── run_qwen2.5-0.5b_gsm8k_multiturn_w_interaction.sh │ ├── run_qwen2.5-3b_gsm8k_multiturn.sh │ ├── run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh │ ├── run_qwen2.5-3b_gsm8k_tool_agent_mlflow.sh │ ├── run_qwen2.5-3b_megatron_gsm8k_multiturn.sh │ ├── run_qwen2_3b_dapo_multiturn.sh │ ├── run_qwen3-4b_gsm8k_multiturn.sh │ └── search_r1_like │ │ ├── local_dense_retriever │ │ ├── download.py │ │ └── retrieval_server.py │ │ └── run_qwen2.5-3b_instruct_search_multiturn.sh ├── slurm │ └── ray_on_slurm.slurm ├── split_placement │ ├── README.md │ ├── config │ │ └── ppo_trainer_split.yaml │ ├── main_ppo_split.py │ ├── run_deepseek7b_llm.sh │ └── split_monkey_patch.py └── tuning │ ├── 0.5b │ └── qwen2-0.5b_grpo-lora_1_h100_fsdp_vllm.sh │ ├── 1.5b │ └── qwen2-1.5b_grpo-lora_1_h100_fsdp_vllm.sh │ ├── 14b │ ├── qwen2-14b_grpo-lora_2_h100_fsdp_vllm.sh │ └── qwen2_14b_grpo_4_h800_fsdp_vllm.sh │ ├── 32b │ ├── qwen2-32b_grpo-lora_4_h100_fsdp_vllm.sh │ └── qwen2_32B_grpo_8_h20_megatron_vllm.sh │ ├── 3b │ └── qwen2-3b_grpo-lora_1_h100_fsdp_vllm.sh │ ├── 70b │ ├── qwen2-70b_grpo_32_h20_fsdp_vllm.sh │ ├── qwen2-70b_grpo_32_h800_fsdp_vllm.sh │ └── qwen2-72b_grpo-lora_8_h100_fsdp_vllm.sh │ └── 7b │ ├── qwen2-7b_grpo-lora_1_h100_fsdp_vllm.sh │ └── qwen2-7b_grpo_2_h800_fsdp_vllm.sh ├── prompt_gen_grpo_flame_sglang_f1_explore.sh ├── prompt_gen_postprocess.py ├── prompt_gen_preprocess.py ├── promptmii.py ├── pyproject.toml ├── run_baselines_modular_sglang.sh ├── run_prompt_gen_postprocess.sh ├── run_prompt_gen_preprocess.sh ├── run_verl_preprocess.sh ├── scripts ├── __init__.py ├── converter_hf_to_mcore.py ├── diagnose.py ├── generate_trainer_config.sh ├── init_random_model.py ├── install_vllm_sglang_mcore.sh ├── legacy_model_merger.py ├── print_cfg.py └── rollout_viewer.py ├── setup.py ├── test_promptmii.py ├── ultra_clean_csv.py ├── verl ├── __init__.py ├── base_config.py ├── experimental │ ├── __init__.py │ ├── agent_loop │ │ ├── __init__.py │ │ ├── agent_loop.py │ │ ├── single_turn_agent_loop.py │ │ ├── tool_agent_loop.py │ │ └── tool_parser.py │ ├── dataset │ │ ├── __init__.py │ │ └── sampler.py │ └── dynamic_dataset │ │ ├── __init__.py │ │ └── dynamicgen_dataset.py ├── interactions │ ├── __init__.py │ ├── base.py │ ├── gsm8k_interaction.py │ └── utils │ │ ├── __init__.py │ │ └── interaction_registry.py ├── model_merger │ ├── __init__.py │ ├── __main__.py │ ├── base_model_merger.py │ ├── fsdp_model_merger.py │ └── megatron_model_merger.py ├── models │ ├── README.md │ ├── __init__.py │ ├── llama │ │ ├── __init__.py │ │ └── megatron │ │ │ ├── __init__.py │ │ │ ├── checkpoint_utils │ │ │ ├── __init__.py │ │ │ ├── llama_loader.py │ │ │ ├── llama_loader_depracated.py │ │ │ └── llama_saver.py │ │ │ ├── layers │ │ │ ├── __init__.py │ │ │ ├── parallel_attention.py │ │ │ ├── parallel_decoder.py │ │ │ ├── parallel_linear.py │ │ │ ├── parallel_mlp.py │ │ │ └── parallel_rmsnorm.py │ │ │ └── modeling_llama_megatron.py │ ├── mcore │ │ ├── __init__.py │ │ ├── config_converter.py │ │ ├── loader.py │ │ ├── mbridge.py │ │ ├── model_forward.py │ │ ├── model_forward_fused.py │ │ ├── model_initializer.py │ │ ├── patch_v012.py │ │ ├── qwen2_5_vl │ │ │ ├── __init__.py │ │ │ ├── attention.py │ │ │ ├── model.py │ │ │ ├── rope_utils.py │ │ │ ├── vision_config.py │ │ │ ├── vision_model.py │ │ │ └── vision_transformer_block.py │ │ ├── readme.md │ │ ├── registry.py │ │ ├── saver.py │ │ ├── util.py │ │ └── weight_converter.py │ ├── qwen2 │ │ ├── __init__.py │ │ └── megatron │ │ │ ├── __init__.py │ │ │ ├── checkpoint_utils │ │ │ ├── __init__.py │ │ │ ├── qwen2_loader.py │ │ │ ├── qwen2_loader_depracated.py │ │ │ └── qwen2_saver.py │ │ │ ├── layers │ │ │ ├── __init__.py │ │ │ ├── parallel_attention.py │ │ │ ├── parallel_decoder.py │ │ │ ├── parallel_linear.py │ │ │ ├── parallel_mlp.py │ │ │ └── parallel_rmsnorm.py │ │ │ └── modeling_qwen2_megatron.py │ ├── registry.py │ ├── transformers │ │ ├── __init__.py │ │ ├── dense_common.py │ │ ├── kimi_vl.py │ │ ├── llama.py │ │ ├── monkey_patch.py │ │ ├── npu_patch.py │ │ ├── qwen2.py │ │ ├── qwen2_5_vl.py │ │ └── qwen2_vl.py │ └── weight_loader_registry.py ├── protocol.py ├── py.typed ├── single_controller │ ├── __init__.py │ ├── base │ │ ├── __init__.py │ │ ├── decorator.py │ │ ├── register_center │ │ │ ├── __init__.py │ │ │ └── ray.py │ │ ├── worker.py │ │ └── worker_group.py │ └── ray │ │ ├── __init__.py │ │ └── base.py ├── third_party │ ├── __init__.py │ ├── sglang │ │ ├── __init__.py │ │ └── parallel_state.py │ ├── torch │ │ ├── __init__.py │ │ └── distributed │ │ │ ├── __init__.py │ │ │ ├── _state_dict_utils.py │ │ │ └── checkpoint │ │ │ ├── __init__.py │ │ │ └── state_dict.py │ └── vllm │ │ └── __init__.py ├── tools │ ├── __init__.py │ ├── base_tool.py │ ├── geo3k_tool.py │ ├── gsm8k_tool.py │ ├── mcp_base_tool.py │ ├── mcp_search_tool.py │ ├── sandbox_fusion_tools.py │ ├── schemas.py │ ├── search_tool.py │ └── utils │ │ ├── __init__.py │ │ ├── mcp_clients │ │ ├── McpClientManager.py │ │ └── utils.py │ │ ├── search_r1_like_utils.py │ │ └── tool_registry.py ├── trainer │ ├── __init__.py │ ├── config │ │ ├── __init__.py │ │ ├── _generated_ppo_megatron_trainer.yaml │ │ ├── _generated_ppo_trainer.yaml │ │ ├── actor │ │ │ ├── actor.yaml │ │ │ ├── dp_actor.yaml │ │ │ └── megatron_actor.yaml │ │ ├── algorithm.py │ │ ├── config.py │ │ ├── critic │ │ │ ├── critic.yaml │ │ │ ├── dp_critic.yaml │ │ │ └── megatron_critic.yaml │ │ ├── data │ │ │ └── legacy_data.yaml │ │ ├── evaluation.yaml │ │ ├── generation.yaml │ │ ├── npu_profile │ │ │ └── npu_profile.yaml │ │ ├── ppo_megatron_trainer.yaml │ │ ├── ppo_trainer.yaml │ │ ├── ref │ │ │ ├── dp_ref.yaml │ │ │ ├── megatron_ref.yaml │ │ │ └── ref.yaml │ │ ├── reward_model │ │ │ ├── dp_reward_model.yaml │ │ │ ├── megatron_reward_model.yaml │ │ │ └── reward_model.yaml │ │ ├── rollout │ │ │ └── rollout.yaml │ │ └── sft_trainer.yaml │ ├── constants_ppo.py │ ├── fsdp_sft_trainer.py │ ├── main_eval.py │ ├── main_generation.py │ ├── main_ppo.py │ ├── ppo │ │ ├── __init__.py │ │ ├── core_algos.py │ │ ├── metric_utils.py │ │ ├── ray_trainer.py │ │ └── reward.py │ └── runtime_env.yaml ├── utils │ ├── __init__.py │ ├── activation_offload.py │ ├── api_config.py │ ├── checkpoint │ │ ├── __init__.py │ │ ├── checkpoint_manager.py │ │ ├── fsdp_checkpoint_manager.py │ │ └── megatron_checkpoint_manager.py │ ├── config.py │ ├── dataset │ │ ├── README.md │ │ ├── __init__.py │ │ ├── multiturn_sft_dataset.py │ │ ├── rl_dataset.py │ │ ├── rm_dataset.py │ │ ├── sft_dataset.py │ │ └── vision_utils.py │ ├── debug │ │ ├── __init__.py │ │ ├── metrics.py │ │ ├── performance.py │ │ └── trajectory_tracker.py │ ├── device.py │ ├── distributed.py │ ├── experimental │ │ ├── __init__.py │ │ └── torch_functional.py │ ├── flops_counter.py │ ├── fs.py │ ├── fsdp_utils.py │ ├── hdfs_io.py │ ├── import_utils.py │ ├── kernel │ │ ├── __init__.py │ │ ├── kernels.py │ │ └── linear_cross_entropy.py │ ├── logger │ │ ├── __init__.py │ │ └── aggregate_logger.py │ ├── logging_utils.py │ ├── megatron │ │ ├── __init__.py │ │ ├── dist_checkpointing.py │ │ ├── memory.py │ │ ├── optimizer.py │ │ ├── pipeline_parallel.py │ │ ├── sequence_parallel.py │ │ └── tensor_parallel.py │ ├── megatron_utils.py │ ├── memory_buffer.py │ ├── memory_utils.py │ ├── metric │ │ ├── __init__.py │ │ └── utils.py │ ├── model.py │ ├── net_utils.py │ ├── profiler │ │ ├── __init__.py │ │ ├── config.py │ │ ├── empty_annotations.py │ │ ├── mstx_profile.py │ │ ├── nvtx_profile.py │ │ ├── performance.py │ │ └── profile.py │ ├── py_functional.py │ ├── ray_utils.py │ ├── rendezvous │ │ ├── __init__.py │ │ └── ray_backend.py │ ├── reward_score │ │ ├── __init__.py │ │ ├── geo3k.py │ │ ├── gsm8k.py │ │ ├── math_batch.py │ │ ├── math_dapo.py │ │ ├── math_utils.py │ │ ├── math_verify.py │ │ ├── prime_code │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── testing_util.py │ │ │ └── utils.py │ │ ├── prime_math │ │ │ ├── __init__.py │ │ │ ├── grader.py │ │ │ └── math_normalize.py │ │ ├── prompt_gen_batch_sglang_v4_fast_f1.py │ │ ├── sandbox_fusion │ │ │ ├── __init__.py │ │ │ └── utils.py │ │ └── search_r1_like_qa_em.py │ ├── rollout_skip.py │ ├── rollout_trace.py │ ├── seqlen_balancing.py │ ├── tokenizer.py │ ├── torch_dtypes.py │ ├── torch_functional.py │ ├── tracking.py │ ├── transformers_compat.py │ ├── ulysses.py │ └── vllm │ │ ├── __init__.py │ │ ├── patch.py │ │ └── utils.py ├── version │ └── version └── workers │ ├── __init__.py │ ├── actor │ ├── __init__.py │ ├── base.py │ ├── dp_actor.py │ └── megatron_actor.py │ ├── config │ ├── __init__.py │ ├── actor.py │ ├── critic.py │ ├── engine.py │ └── optimizer.py │ ├── critic │ ├── __init__.py │ ├── base.py │ ├── dp_critic.py │ └── megatron_critic.py │ ├── engine │ ├── __init__.py │ ├── base.py │ ├── fsdp │ │ ├── __init__.py │ │ ├── engine_impl.py │ │ └── utils.py │ └── megatron │ │ ├── __init__.py │ │ └── engine_impl.py │ ├── fsdp_workers.py │ ├── megatron_workers.py │ ├── reward_manager │ ├── __init__.py │ ├── abstract.py │ ├── batch.py │ ├── dapo.py │ ├── naive.py │ ├── prime.py │ └── registry.py │ ├── reward_model │ ├── __init__.py │ ├── base.py │ └── megatron │ │ ├── __init__.py │ │ └── reward_model.py │ ├── roles │ ├── __init__.py │ ├── actor.py │ └── critic.py │ ├── rollout │ ├── __init__.py │ ├── async_server.py │ ├── base.py │ ├── hf_rollout.py │ ├── naive │ │ ├── __init__.py │ │ └── naive_rollout.py │ ├── schemas.py │ ├── sglang_rollout │ │ ├── __init__.py │ │ ├── async_sglang_server.py │ │ ├── sglang_rollout.py │ │ └── utils.py │ ├── tokenizer.py │ └── vllm_rollout │ │ ├── __init__.py │ │ ├── vllm_async_server.py │ │ └── vllm_rollout_spmd.py │ └── sharding_manager │ ├── __init__.py │ ├── base.py │ ├── fsdp_sglang.py │ ├── fsdp_ulysses.py │ ├── fsdp_vllm.py │ ├── megatron_sglang.py │ └── megatron_vllm.py ├── verl_readme.md └── view_preprocessed_data.py /.gemini/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.gemini/config.yaml -------------------------------------------------------------------------------- /.github/CODEOWNERS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/CODEOWNERS -------------------------------------------------------------------------------- /.github/PULL_REQUEST_TEMPLATE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/PULL_REQUEST_TEMPLATE.md -------------------------------------------------------------------------------- /.github/dependabot.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/dependabot.yml -------------------------------------------------------------------------------- /.github/workflows/.deprecate/e2e_ppo_trainer.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/.deprecate/e2e_ppo_trainer.yml -------------------------------------------------------------------------------- /.github/workflows/.deprecate/e2e_ppo_trainer_megatron_sglang.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/.deprecate/e2e_ppo_trainer_megatron_sglang.yml -------------------------------------------------------------------------------- /.github/workflows/.deprecate/e2e_prime.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/.deprecate/e2e_prime.yml -------------------------------------------------------------------------------- /.github/workflows/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/README.md -------------------------------------------------------------------------------- /.github/workflows/check-pr-title.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/check-pr-title.yml -------------------------------------------------------------------------------- /.github/workflows/checkpoint_converter.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/checkpoint_converter.yml -------------------------------------------------------------------------------- /.github/workflows/cpu_unit_tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/cpu_unit_tests.yml -------------------------------------------------------------------------------- /.github/workflows/doc.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/doc.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_ascend.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_ascend.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_dapo.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_dapo.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_eval_aime24.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_eval_aime24.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_genrm_remote.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_genrm_remote.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_one_step_off_policy.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_one_step_off_policy.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_ppo_trainer.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_ppo_trainer.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_ppo_trainer_megatron_sglang.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_ppo_trainer_megatron_sglang.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_ppo_trainer_megatron_vllm.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_ppo_trainer_megatron_vllm.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_sft.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_sft.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_spin.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_spin.yml -------------------------------------------------------------------------------- /.github/workflows/e2e_sppo.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/e2e_sppo.yml -------------------------------------------------------------------------------- /.github/workflows/gpu_unit_tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/gpu_unit_tests.yml -------------------------------------------------------------------------------- /.github/workflows/model.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/model.yml -------------------------------------------------------------------------------- /.github/workflows/pre-commit-full.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/pre-commit-full.yml -------------------------------------------------------------------------------- /.github/workflows/pre-commit.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/pre-commit.yml -------------------------------------------------------------------------------- /.github/workflows/sanity.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/sanity.yml -------------------------------------------------------------------------------- /.github/workflows/scorecard.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/scorecard.yml -------------------------------------------------------------------------------- /.github/workflows/secrets_scan.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/secrets_scan.yml -------------------------------------------------------------------------------- /.github/workflows/sgl.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/sgl.yml -------------------------------------------------------------------------------- /.github/workflows/type-coverage-check.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/type-coverage-check.yml -------------------------------------------------------------------------------- /.github/workflows/vllm.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.github/workflows/vllm.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /.readthedocs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/.readthedocs.yaml -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/README.md -------------------------------------------------------------------------------- /add_api_instruction_baseline_sglang.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/add_api_instruction_baseline_sglang.sh -------------------------------------------------------------------------------- /add_trained_instruction_baseline_sglang.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/add_trained_instruction_baseline_sglang.sh -------------------------------------------------------------------------------- /analyze_baseline_results_f1_macro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/analyze_baseline_results_f1_macro.py -------------------------------------------------------------------------------- /api_instruction_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/api_instruction_helper.py -------------------------------------------------------------------------------- /baseline_eval_v3_modular.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/baseline_eval_v3_modular.py -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/README.md -------------------------------------------------------------------------------- /docs/README_vllm0.7.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/README_vllm0.7.md -------------------------------------------------------------------------------- /docs/README_vllm0.8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/README_vllm0.8.md -------------------------------------------------------------------------------- /docs/_static/custom.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/_static/custom.css -------------------------------------------------------------------------------- /docs/_static/js/resizable-sidebar.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/_static/js/resizable-sidebar.js -------------------------------------------------------------------------------- /docs/_static/js/runllm-widget.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/_static/js/runllm-widget.js -------------------------------------------------------------------------------- /docs/_static/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/_static/logo.png -------------------------------------------------------------------------------- /docs/advance/agent_loop.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/agent_loop.rst -------------------------------------------------------------------------------- /docs/advance/checkpoint.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/checkpoint.rst -------------------------------------------------------------------------------- /docs/advance/dpo_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/dpo_extension.rst -------------------------------------------------------------------------------- /docs/advance/fsdp_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/fsdp_extension.rst -------------------------------------------------------------------------------- /docs/advance/megatron_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/megatron_extension.rst -------------------------------------------------------------------------------- /docs/advance/one_step_off.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/one_step_off.md -------------------------------------------------------------------------------- /docs/advance/placement.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/placement.rst -------------------------------------------------------------------------------- /docs/advance/ppo_lora.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/ppo_lora.rst -------------------------------------------------------------------------------- /docs/advance/rollout_skip.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/rollout_skip.rst -------------------------------------------------------------------------------- /docs/advance/rollout_trace.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/rollout_trace.rst -------------------------------------------------------------------------------- /docs/advance/rope.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/advance/rope.rst -------------------------------------------------------------------------------- /docs/algo/baseline.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/baseline.md -------------------------------------------------------------------------------- /docs/algo/dapo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/dapo.md -------------------------------------------------------------------------------- /docs/algo/entropy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/entropy.md -------------------------------------------------------------------------------- /docs/algo/gpg.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/gpg.md -------------------------------------------------------------------------------- /docs/algo/grpo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/grpo.md -------------------------------------------------------------------------------- /docs/algo/opo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/opo.md -------------------------------------------------------------------------------- /docs/algo/ppo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/ppo.md -------------------------------------------------------------------------------- /docs/algo/spin.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/spin.md -------------------------------------------------------------------------------- /docs/algo/sppo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/algo/sppo.md -------------------------------------------------------------------------------- /docs/amd_tutorial/amd_build_dockerfile_page.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/amd_tutorial/amd_build_dockerfile_page.rst -------------------------------------------------------------------------------- /docs/amd_tutorial/amd_vllm_page.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/amd_tutorial/amd_vllm_page.rst -------------------------------------------------------------------------------- /docs/api/data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/api/data.rst -------------------------------------------------------------------------------- /docs/api/single_controller.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/api/single_controller.rst -------------------------------------------------------------------------------- /docs/api/trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/api/trainer.rst -------------------------------------------------------------------------------- /docs/api/utils.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/api/utils.rst -------------------------------------------------------------------------------- /docs/ascend_tutorial/ascend_profiling.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/ascend_tutorial/ascend_profiling.rst -------------------------------------------------------------------------------- /docs/ascend_tutorial/ascend_profiling_en.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/ascend_tutorial/ascend_profiling_en.rst -------------------------------------------------------------------------------- /docs/ascend_tutorial/ascend_quick_start.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/ascend_tutorial/ascend_quick_start.rst -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/examples/config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/examples/config.rst -------------------------------------------------------------------------------- /docs/examples/gsm8k_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/examples/gsm8k_example.rst -------------------------------------------------------------------------------- /docs/examples/multi_modal_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/examples/multi_modal_example.rst -------------------------------------------------------------------------------- /docs/examples/ppo_code_architecture.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/examples/ppo_code_architecture.rst -------------------------------------------------------------------------------- /docs/examples/sandbox_fusion_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/examples/sandbox_fusion_example.rst -------------------------------------------------------------------------------- /docs/faq/faq.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/faq/faq.rst -------------------------------------------------------------------------------- /docs/hybrid_flow.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/hybrid_flow.rst -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/index.rst -------------------------------------------------------------------------------- /docs/perf/device_tuning.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/perf/device_tuning.rst -------------------------------------------------------------------------------- /docs/perf/dpsk.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/perf/dpsk.md -------------------------------------------------------------------------------- /docs/perf/nsight_profiling.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/perf/nsight_profiling.md -------------------------------------------------------------------------------- /docs/perf/perf_tuning.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/perf/perf_tuning.rst -------------------------------------------------------------------------------- /docs/preparation/prepare_data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/preparation/prepare_data.rst -------------------------------------------------------------------------------- /docs/preparation/reward_function.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/preparation/reward_function.rst -------------------------------------------------------------------------------- /docs/requirements-docs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/requirements-docs.txt -------------------------------------------------------------------------------- /docs/sglang_multiturn/interaction_system.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/sglang_multiturn/interaction_system.rst -------------------------------------------------------------------------------- /docs/sglang_multiturn/multiturn.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/sglang_multiturn/multiturn.rst -------------------------------------------------------------------------------- /docs/sglang_multiturn/sandbox_fusion.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/sglang_multiturn/sandbox_fusion.rst -------------------------------------------------------------------------------- /docs/sglang_multiturn/search_tool_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/sglang_multiturn/search_tool_example.rst -------------------------------------------------------------------------------- /docs/single_controller.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/single_controller.rst -------------------------------------------------------------------------------- /docs/start/agentic_rl.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/start/agentic_rl.rst -------------------------------------------------------------------------------- /docs/start/install.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/start/install.rst -------------------------------------------------------------------------------- /docs/start/more_resources.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/start/more_resources.rst -------------------------------------------------------------------------------- /docs/start/multinode.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/start/multinode.rst -------------------------------------------------------------------------------- /docs/start/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/start/quickstart.rst -------------------------------------------------------------------------------- /docs/start/ray_debug_tutorial.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/start/ray_debug_tutorial.rst -------------------------------------------------------------------------------- /docs/workers/fsdp_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/workers/fsdp_workers.rst -------------------------------------------------------------------------------- /docs/workers/megatron_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/workers/megatron_workers.rst -------------------------------------------------------------------------------- /docs/workers/ray_trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/workers/ray_trainer.rst -------------------------------------------------------------------------------- /docs/workers/sglang_worker.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/docs/workers/sglang_worker.rst -------------------------------------------------------------------------------- /env.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/env.yml -------------------------------------------------------------------------------- /examples/data_preprocess/aime2024_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/aime2024_multiturn_w_tool.py -------------------------------------------------------------------------------- /examples/data_preprocess/dapo_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/dapo_multiturn_w_tool.py -------------------------------------------------------------------------------- /examples/data_preprocess/full_hh_rlhf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/full_hh_rlhf.py -------------------------------------------------------------------------------- /examples/data_preprocess/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/geo3k.py -------------------------------------------------------------------------------- /examples/data_preprocess/geo3k_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/geo3k_multiturn_w_tool.py -------------------------------------------------------------------------------- /examples/data_preprocess/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/gsm8k.py -------------------------------------------------------------------------------- /examples/data_preprocess/gsm8k_multiturn_w_interaction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/gsm8k_multiturn_w_interaction.py -------------------------------------------------------------------------------- /examples/data_preprocess/gsm8k_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/gsm8k_multiturn_w_tool.py -------------------------------------------------------------------------------- /examples/data_preprocess/gsm8k_tool_agent_loop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/gsm8k_tool_agent_loop.py -------------------------------------------------------------------------------- /examples/data_preprocess/hellaswag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/hellaswag.py -------------------------------------------------------------------------------- /examples/data_preprocess/math_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/math_dataset.py -------------------------------------------------------------------------------- /examples/data_preprocess/multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/multiturn.py -------------------------------------------------------------------------------- /examples/data_preprocess/preprocess_search_r1_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/preprocess_search_r1_dataset.py -------------------------------------------------------------------------------- /examples/data_preprocess/prompt_gen_v8.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/data_preprocess/prompt_gen_v8.py -------------------------------------------------------------------------------- /examples/generation/run_deepseek7b_mutli_node.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/generation/run_deepseek7b_mutli_node.sh -------------------------------------------------------------------------------- /examples/generation/run_deepseek_v2_lite_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/generation/run_deepseek_v2_lite_math.sh -------------------------------------------------------------------------------- /examples/gmpo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/gmpo_trainer/README.md -------------------------------------------------------------------------------- /examples/gmpo_trainer/run_qwen2_5-7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/gmpo_trainer/run_qwen2_5-7b_math.sh -------------------------------------------------------------------------------- /examples/gmpo_trainer/test_dapo_7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/gmpo_trainer/test_dapo_7b_math.sh -------------------------------------------------------------------------------- /examples/gmpo_trainer/test_dapo_qwen3_30b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/gmpo_trainer/test_dapo_qwen3_30b_math.sh -------------------------------------------------------------------------------- /examples/gpg_trainer/gpg.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/gpg_trainer/gpg.md -------------------------------------------------------------------------------- /examples/gpg_trainer/run_qwen2-7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/gpg_trainer/run_qwen2-7b_math.sh -------------------------------------------------------------------------------- /examples/gpg_trainer/run_qwen2-7b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/gpg_trainer/run_qwen2-7b_math_megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/README.md -------------------------------------------------------------------------------- /examples/grpo_trainer/run_deepseek671b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_deepseek671b_math_megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_deepseek7b_llm_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_deepseek7b_llm_math.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_deepseek7b_llm_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_deepseek7b_llm_math_megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_deepseek7b_llm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_deepseek7b_llm_seq_balance.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_minicpmo2_6.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_minicpmo2_6.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_moonlight16b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_moonlight16b_math_megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2-7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2-7b_math.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2-7b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2-7b_math_megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2-7b_seq_balance_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2-7b_seq_balance_math_megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2-7b_sgl_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2-7b_sgl_megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5-3b_gsm8k_grpo_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5-3b_gsm8k_grpo_lora.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5-7b_math_megatron_diff_tp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5-7b_math_megatron_diff_tp.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_32b_grpo_npu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_32b_grpo_npu.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_7b_grpo_discrete_prof_npu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_7b_grpo_discrete_prof_npu.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_7b_grpo_e2e_prof_npu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_7b_grpo_e2e_prof_npu.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_7b_grpo_npu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_7b_grpo_npu.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_vl-7b-megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_vl-7b-megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_vl-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_vl-7b.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_vl-7b_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_vl-7b_lora.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_vl-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_vl-7b_seq_balance.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_vl_32b_npu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_vl_32b_npu.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_vl_3b_npu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_vl_3b_npu.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen2_5_vl_7b_npu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen2_5_vl_7b_npu.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen3-236b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen3-236b_megatron.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen3-8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen3-8b.sh -------------------------------------------------------------------------------- /examples/grpo_trainer/run_qwen3moe-30b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/grpo_trainer/run_qwen3moe-30b_megatron.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/README.md -------------------------------------------------------------------------------- /examples/ppo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_deepseek7b_llm_modelscope.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_deepseek7b_llm_modelscope.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_deepseek7b_llm_pfppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_deepseek7b_llm_pfppo.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_deepseek7b_llm_sandbox_fusion.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_deepseek7b_llm_sandbox_fusion.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_deepseek7b_llm_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_deepseek_math_gsm8k_megatron_nsys.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron_nsys.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_gemma.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_gemma.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_moonlight16b_a3b_gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_moonlight16b_a3b_gsm8k_megatron.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen2-7b_math_gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen2-7b_math_gsm8k_megatron.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen2-7b_rm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen2-7b_rm.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen2-7b_rm_seq_balance_fused_kernels.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance_fused_kernels.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen2-7b_rm_seq_balance_nsys.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance_nsys.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen2-7b_sglang_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen2-7b_sglang_seq_balance.sh -------------------------------------------------------------------------------- /examples/ppo_trainer/run_qwen2.5-32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ppo_trainer/run_qwen2.5-32b.sh -------------------------------------------------------------------------------- /examples/ray/tutorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/ray/tutorial.ipynb -------------------------------------------------------------------------------- /examples/reinforce_plus_plus_trainer/run_qwen2-7b_math_rf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/reinforce_plus_plus_trainer/run_qwen2-7b_math_rf.sh -------------------------------------------------------------------------------- /examples/reinforce_plus_plus_trainer/run_qwen2-7b_math_rf_baseline.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/reinforce_plus_plus_trainer/run_qwen2-7b_math_rf_baseline.sh -------------------------------------------------------------------------------- /examples/remax_trainer/run_qwen2.5-3b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/remax_trainer/run_qwen2.5-3b_seq_balance.sh -------------------------------------------------------------------------------- /examples/remax_trainer/run_qwen2.5-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/remax_trainer/run_qwen2.5-7b_seq_balance.sh -------------------------------------------------------------------------------- /examples/rloo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/rloo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /examples/sft/gsm8k/run_deepseek_6b7.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sft/gsm8k/run_deepseek_6b7.sh -------------------------------------------------------------------------------- /examples/sft/gsm8k/run_gemma_2b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sft/gsm8k/run_gemma_2b.sh -------------------------------------------------------------------------------- /examples/sft/gsm8k/run_gemma_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sft/gsm8k/run_gemma_7b.sh -------------------------------------------------------------------------------- /examples/sft/gsm8k/run_qwen2_5_05b_sft_peft_sp2_npu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sft/gsm8k/run_qwen2_5_05b_sft_peft_sp2_npu.sh -------------------------------------------------------------------------------- /examples/sft/gsm8k/run_qwen_05_peft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sft/gsm8k/run_qwen_05_peft.sh -------------------------------------------------------------------------------- /examples/sft/gsm8k/run_qwen_05_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sft/gsm8k/run_qwen_05_sp2.sh -------------------------------------------------------------------------------- /examples/sft/gsm8k/run_qwen_05_sp2_liger.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sft/gsm8k/run_qwen_05_sp2_liger.sh -------------------------------------------------------------------------------- /examples/sft/multiturn/run_qwen_05_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sft/multiturn/run_qwen_05_sp2.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/README.md -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/geo3k_multiturn_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/geo3k_multiturn_grpo.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/geo3k_multiturn_megatron_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/geo3k_multiturn_megatron_grpo.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/gsm8k_multiturn_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/gsm8k_multiturn_grpo.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/gsm8k_multiturn_grpo_w_interaction.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/gsm8k_multiturn_grpo_w_interaction.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/gsm8k_multiturn_megatron_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/gsm8k_multiturn_megatron_grpo.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/interaction_config/gsm8k_interaction_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/interaction_config/gsm8k_interaction_config.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/retool_multiturn_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/retool_multiturn_grpo.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/search_multiturn_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/search_multiturn_grpo.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/tool_config/geo3k_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/tool_config/geo3k_tool_config.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/tool_config/gsm8k_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/tool_config/gsm8k_tool_config.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/tool_config/mcp_server.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/tool_config/mcp_server.json -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/tool_config/mcp_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/tool_config/mcp_tool_config.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/tool_config/sandbox_fusion_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/tool_config/sandbox_fusion_tool_config.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/config/tool_config/search_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/config/tool_config/search_tool_config.yaml -------------------------------------------------------------------------------- /examples/sglang_multiturn/geo3k/run_qwen2.5-3b_geo3k_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/geo3k/run_qwen2.5-3b_geo3k_multiturn.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/geo3k/run_qwen2.5-3b_geo3k_multiturn_4xgpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/geo3k/run_qwen2.5-3b_geo3k_multiturn_4xgpu.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/geo3k/run_qwen2.5-3b_megatron_geo3k_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/geo3k/run_qwen2.5-3b_megatron_geo3k_multiturn.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/run_qwen0.5b_gsm8k_multiturn_curriculum.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/run_qwen0.5b_gsm8k_multiturn_curriculum.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/run_qwen2.5-0.5b_gsm8k_multiturn_w_interaction.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/run_qwen2.5-0.5b_gsm8k_multiturn_w_interaction.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_multiturn.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_tool_agent_mlflow.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_tool_agent_mlflow.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/run_qwen2.5-3b_megatron_gsm8k_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/run_qwen2.5-3b_megatron_gsm8k_multiturn.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/run_qwen2_3b_dapo_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/run_qwen2_3b_dapo_multiturn.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/run_qwen3-4b_gsm8k_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/run_qwen3-4b_gsm8k_multiturn.sh -------------------------------------------------------------------------------- /examples/sglang_multiturn/search_r1_like/local_dense_retriever/download.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/search_r1_like/local_dense_retriever/download.py -------------------------------------------------------------------------------- /examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.py -------------------------------------------------------------------------------- /examples/sglang_multiturn/search_r1_like/run_qwen2.5-3b_instruct_search_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/sglang_multiturn/search_r1_like/run_qwen2.5-3b_instruct_search_multiturn.sh -------------------------------------------------------------------------------- /examples/slurm/ray_on_slurm.slurm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/slurm/ray_on_slurm.slurm -------------------------------------------------------------------------------- /examples/split_placement/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/split_placement/README.md -------------------------------------------------------------------------------- /examples/split_placement/config/ppo_trainer_split.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/split_placement/config/ppo_trainer_split.yaml -------------------------------------------------------------------------------- /examples/split_placement/main_ppo_split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/split_placement/main_ppo_split.py -------------------------------------------------------------------------------- /examples/split_placement/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/split_placement/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /examples/split_placement/split_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/split_placement/split_monkey_patch.py -------------------------------------------------------------------------------- /examples/tuning/0.5b/qwen2-0.5b_grpo-lora_1_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/0.5b/qwen2-0.5b_grpo-lora_1_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/1.5b/qwen2-1.5b_grpo-lora_1_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/1.5b/qwen2-1.5b_grpo-lora_1_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/14b/qwen2-14b_grpo-lora_2_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/14b/qwen2-14b_grpo-lora_2_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/14b/qwen2_14b_grpo_4_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/14b/qwen2_14b_grpo_4_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/32b/qwen2-32b_grpo-lora_4_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/32b/qwen2-32b_grpo-lora_4_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/32b/qwen2_32B_grpo_8_h20_megatron_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/32b/qwen2_32B_grpo_8_h20_megatron_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/3b/qwen2-3b_grpo-lora_1_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/3b/qwen2-3b_grpo-lora_1_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/70b/qwen2-70b_grpo_32_h20_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/70b/qwen2-70b_grpo_32_h20_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/70b/qwen2-70b_grpo_32_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/70b/qwen2-70b_grpo_32_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/70b/qwen2-72b_grpo-lora_8_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/70b/qwen2-72b_grpo-lora_8_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/7b/qwen2-7b_grpo-lora_1_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/7b/qwen2-7b_grpo-lora_1_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /examples/tuning/7b/qwen2-7b_grpo_2_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/examples/tuning/7b/qwen2-7b_grpo_2_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /prompt_gen_grpo_flame_sglang_f1_explore.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/prompt_gen_grpo_flame_sglang_f1_explore.sh -------------------------------------------------------------------------------- /prompt_gen_postprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/prompt_gen_postprocess.py -------------------------------------------------------------------------------- /prompt_gen_preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/prompt_gen_preprocess.py -------------------------------------------------------------------------------- /promptmii.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/promptmii.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/pyproject.toml -------------------------------------------------------------------------------- /run_baselines_modular_sglang.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/run_baselines_modular_sglang.sh -------------------------------------------------------------------------------- /run_prompt_gen_postprocess.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/run_prompt_gen_postprocess.sh -------------------------------------------------------------------------------- /run_prompt_gen_preprocess.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/run_prompt_gen_preprocess.sh -------------------------------------------------------------------------------- /run_verl_preprocess.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/run_verl_preprocess.sh -------------------------------------------------------------------------------- /scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/__init__.py -------------------------------------------------------------------------------- /scripts/converter_hf_to_mcore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/converter_hf_to_mcore.py -------------------------------------------------------------------------------- /scripts/diagnose.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/diagnose.py -------------------------------------------------------------------------------- /scripts/generate_trainer_config.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/generate_trainer_config.sh -------------------------------------------------------------------------------- /scripts/init_random_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/init_random_model.py -------------------------------------------------------------------------------- /scripts/install_vllm_sglang_mcore.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/install_vllm_sglang_mcore.sh -------------------------------------------------------------------------------- /scripts/legacy_model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/legacy_model_merger.py -------------------------------------------------------------------------------- /scripts/print_cfg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/print_cfg.py -------------------------------------------------------------------------------- /scripts/rollout_viewer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/scripts/rollout_viewer.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/setup.py -------------------------------------------------------------------------------- /test_promptmii.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/test_promptmii.py -------------------------------------------------------------------------------- /ultra_clean_csv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/ultra_clean_csv.py -------------------------------------------------------------------------------- /verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/__init__.py -------------------------------------------------------------------------------- /verl/base_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/base_config.py -------------------------------------------------------------------------------- /verl/experimental/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/__init__.py -------------------------------------------------------------------------------- /verl/experimental/agent_loop/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/agent_loop/__init__.py -------------------------------------------------------------------------------- /verl/experimental/agent_loop/agent_loop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/agent_loop/agent_loop.py -------------------------------------------------------------------------------- /verl/experimental/agent_loop/single_turn_agent_loop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/agent_loop/single_turn_agent_loop.py -------------------------------------------------------------------------------- /verl/experimental/agent_loop/tool_agent_loop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/agent_loop/tool_agent_loop.py -------------------------------------------------------------------------------- /verl/experimental/agent_loop/tool_parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/agent_loop/tool_parser.py -------------------------------------------------------------------------------- /verl/experimental/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/dataset/__init__.py -------------------------------------------------------------------------------- /verl/experimental/dataset/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/dataset/sampler.py -------------------------------------------------------------------------------- /verl/experimental/dynamic_dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/dynamic_dataset/__init__.py -------------------------------------------------------------------------------- /verl/experimental/dynamic_dataset/dynamicgen_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/experimental/dynamic_dataset/dynamicgen_dataset.py -------------------------------------------------------------------------------- /verl/interactions/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/interactions/__init__.py -------------------------------------------------------------------------------- /verl/interactions/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/interactions/base.py -------------------------------------------------------------------------------- /verl/interactions/gsm8k_interaction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/interactions/gsm8k_interaction.py -------------------------------------------------------------------------------- /verl/interactions/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/interactions/utils/__init__.py -------------------------------------------------------------------------------- /verl/interactions/utils/interaction_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/interactions/utils/interaction_registry.py -------------------------------------------------------------------------------- /verl/model_merger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/model_merger/__init__.py -------------------------------------------------------------------------------- /verl/model_merger/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/model_merger/__main__.py -------------------------------------------------------------------------------- /verl/model_merger/base_model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/model_merger/base_model_merger.py -------------------------------------------------------------------------------- /verl/model_merger/fsdp_model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/model_merger/fsdp_model_merger.py -------------------------------------------------------------------------------- /verl/model_merger/megatron_model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/model_merger/megatron_model_merger.py -------------------------------------------------------------------------------- /verl/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/README.md -------------------------------------------------------------------------------- /verl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/checkpoint_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/checkpoint_utils/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/checkpoint_utils/llama_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/checkpoint_utils/llama_loader.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/checkpoint_utils/llama_loader_depracated.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/checkpoint_utils/llama_loader_depracated.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/checkpoint_utils/llama_saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/checkpoint_utils/llama_saver.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/layers/parallel_attention.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/modeling_llama_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/llama/megatron/modeling_llama_megatron.py -------------------------------------------------------------------------------- /verl/models/mcore/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/__init__.py -------------------------------------------------------------------------------- /verl/models/mcore/config_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/config_converter.py -------------------------------------------------------------------------------- /verl/models/mcore/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/loader.py -------------------------------------------------------------------------------- /verl/models/mcore/mbridge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/mbridge.py -------------------------------------------------------------------------------- /verl/models/mcore/model_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/model_forward.py -------------------------------------------------------------------------------- /verl/models/mcore/model_forward_fused.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/model_forward_fused.py -------------------------------------------------------------------------------- /verl/models/mcore/model_initializer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/model_initializer.py -------------------------------------------------------------------------------- /verl/models/mcore/patch_v012.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/patch_v012.py -------------------------------------------------------------------------------- /verl/models/mcore/qwen2_5_vl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/qwen2_5_vl/__init__.py -------------------------------------------------------------------------------- /verl/models/mcore/qwen2_5_vl/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/qwen2_5_vl/attention.py -------------------------------------------------------------------------------- /verl/models/mcore/qwen2_5_vl/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/qwen2_5_vl/model.py -------------------------------------------------------------------------------- /verl/models/mcore/qwen2_5_vl/rope_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/qwen2_5_vl/rope_utils.py -------------------------------------------------------------------------------- /verl/models/mcore/qwen2_5_vl/vision_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/qwen2_5_vl/vision_config.py -------------------------------------------------------------------------------- /verl/models/mcore/qwen2_5_vl/vision_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/qwen2_5_vl/vision_model.py -------------------------------------------------------------------------------- /verl/models/mcore/qwen2_5_vl/vision_transformer_block.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/qwen2_5_vl/vision_transformer_block.py -------------------------------------------------------------------------------- /verl/models/mcore/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/readme.md -------------------------------------------------------------------------------- /verl/models/mcore/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/registry.py -------------------------------------------------------------------------------- /verl/models/mcore/saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/saver.py -------------------------------------------------------------------------------- /verl/models/mcore/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/util.py -------------------------------------------------------------------------------- /verl/models/mcore/weight_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/mcore/weight_converter.py -------------------------------------------------------------------------------- /verl/models/qwen2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/__init__.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/__init__.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/checkpoint_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/checkpoint_utils/__init__.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader_depracated.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader_depracated.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/layers/parallel_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/layers/parallel_attention.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/models/qwen2/megatron/modeling_qwen2_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/qwen2/megatron/modeling_qwen2_megatron.py -------------------------------------------------------------------------------- /verl/models/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/registry.py -------------------------------------------------------------------------------- /verl/models/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/__init__.py -------------------------------------------------------------------------------- /verl/models/transformers/dense_common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/dense_common.py -------------------------------------------------------------------------------- /verl/models/transformers/kimi_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/kimi_vl.py -------------------------------------------------------------------------------- /verl/models/transformers/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/llama.py -------------------------------------------------------------------------------- /verl/models/transformers/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/monkey_patch.py -------------------------------------------------------------------------------- /verl/models/transformers/npu_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/npu_patch.py -------------------------------------------------------------------------------- /verl/models/transformers/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/qwen2.py -------------------------------------------------------------------------------- /verl/models/transformers/qwen2_5_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/qwen2_5_vl.py -------------------------------------------------------------------------------- /verl/models/transformers/qwen2_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/transformers/qwen2_vl.py -------------------------------------------------------------------------------- /verl/models/weight_loader_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/models/weight_loader_registry.py -------------------------------------------------------------------------------- /verl/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/protocol.py -------------------------------------------------------------------------------- /verl/py.typed: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /verl/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/base/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/base/decorator.py -------------------------------------------------------------------------------- /verl/single_controller/base/register_center/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/base/register_center/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/register_center/ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/base/register_center/ray.py -------------------------------------------------------------------------------- /verl/single_controller/base/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/base/worker.py -------------------------------------------------------------------------------- /verl/single_controller/base/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/base/worker_group.py -------------------------------------------------------------------------------- /verl/single_controller/ray/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/ray/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/ray/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/single_controller/ray/base.py -------------------------------------------------------------------------------- /verl/third_party/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/__init__.py -------------------------------------------------------------------------------- /verl/third_party/sglang/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/sglang/__init__.py -------------------------------------------------------------------------------- /verl/third_party/sglang/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/sglang/parallel_state.py -------------------------------------------------------------------------------- /verl/third_party/torch/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/torch/__init__.py -------------------------------------------------------------------------------- /verl/third_party/torch/distributed/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/torch/distributed/__init__.py -------------------------------------------------------------------------------- /verl/third_party/torch/distributed/_state_dict_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/torch/distributed/_state_dict_utils.py -------------------------------------------------------------------------------- /verl/third_party/torch/distributed/checkpoint/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/torch/distributed/checkpoint/__init__.py -------------------------------------------------------------------------------- /verl/third_party/torch/distributed/checkpoint/state_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/torch/distributed/checkpoint/state_dict.py -------------------------------------------------------------------------------- /verl/third_party/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/third_party/vllm/__init__.py -------------------------------------------------------------------------------- /verl/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/__init__.py -------------------------------------------------------------------------------- /verl/tools/base_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/base_tool.py -------------------------------------------------------------------------------- /verl/tools/geo3k_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/geo3k_tool.py -------------------------------------------------------------------------------- /verl/tools/gsm8k_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/gsm8k_tool.py -------------------------------------------------------------------------------- /verl/tools/mcp_base_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/mcp_base_tool.py -------------------------------------------------------------------------------- /verl/tools/mcp_search_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/mcp_search_tool.py -------------------------------------------------------------------------------- /verl/tools/sandbox_fusion_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/sandbox_fusion_tools.py -------------------------------------------------------------------------------- /verl/tools/schemas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/schemas.py -------------------------------------------------------------------------------- /verl/tools/search_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/search_tool.py -------------------------------------------------------------------------------- /verl/tools/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/utils/__init__.py -------------------------------------------------------------------------------- /verl/tools/utils/mcp_clients/McpClientManager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/utils/mcp_clients/McpClientManager.py -------------------------------------------------------------------------------- /verl/tools/utils/mcp_clients/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/utils/mcp_clients/utils.py -------------------------------------------------------------------------------- /verl/tools/utils/search_r1_like_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/utils/search_r1_like_utils.py -------------------------------------------------------------------------------- /verl/tools/utils/tool_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/tools/utils/tool_registry.py -------------------------------------------------------------------------------- /verl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/__init__.py -------------------------------------------------------------------------------- /verl/trainer/config/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/__init__.py -------------------------------------------------------------------------------- /verl/trainer/config/_generated_ppo_megatron_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/_generated_ppo_megatron_trainer.yaml -------------------------------------------------------------------------------- /verl/trainer/config/_generated_ppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/_generated_ppo_trainer.yaml -------------------------------------------------------------------------------- /verl/trainer/config/actor/actor.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/actor/actor.yaml -------------------------------------------------------------------------------- /verl/trainer/config/actor/dp_actor.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/actor/dp_actor.yaml -------------------------------------------------------------------------------- /verl/trainer/config/actor/megatron_actor.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/actor/megatron_actor.yaml -------------------------------------------------------------------------------- /verl/trainer/config/algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/algorithm.py -------------------------------------------------------------------------------- /verl/trainer/config/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/config.py -------------------------------------------------------------------------------- /verl/trainer/config/critic/critic.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/critic/critic.yaml -------------------------------------------------------------------------------- /verl/trainer/config/critic/dp_critic.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/critic/dp_critic.yaml -------------------------------------------------------------------------------- /verl/trainer/config/critic/megatron_critic.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/critic/megatron_critic.yaml -------------------------------------------------------------------------------- /verl/trainer/config/data/legacy_data.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/data/legacy_data.yaml -------------------------------------------------------------------------------- /verl/trainer/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/evaluation.yaml -------------------------------------------------------------------------------- /verl/trainer/config/generation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/generation.yaml -------------------------------------------------------------------------------- /verl/trainer/config/npu_profile/npu_profile.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/npu_profile/npu_profile.yaml -------------------------------------------------------------------------------- /verl/trainer/config/ppo_megatron_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/ppo_megatron_trainer.yaml -------------------------------------------------------------------------------- /verl/trainer/config/ppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/ppo_trainer.yaml -------------------------------------------------------------------------------- /verl/trainer/config/ref/dp_ref.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/ref/dp_ref.yaml -------------------------------------------------------------------------------- /verl/trainer/config/ref/megatron_ref.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/ref/megatron_ref.yaml -------------------------------------------------------------------------------- /verl/trainer/config/ref/ref.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/ref/ref.yaml -------------------------------------------------------------------------------- /verl/trainer/config/reward_model/dp_reward_model.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/reward_model/dp_reward_model.yaml -------------------------------------------------------------------------------- /verl/trainer/config/reward_model/megatron_reward_model.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/reward_model/megatron_reward_model.yaml -------------------------------------------------------------------------------- /verl/trainer/config/reward_model/reward_model.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/reward_model/reward_model.yaml -------------------------------------------------------------------------------- /verl/trainer/config/rollout/rollout.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/rollout/rollout.yaml -------------------------------------------------------------------------------- /verl/trainer/config/sft_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/config/sft_trainer.yaml -------------------------------------------------------------------------------- /verl/trainer/constants_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/constants_ppo.py -------------------------------------------------------------------------------- /verl/trainer/fsdp_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/fsdp_sft_trainer.py -------------------------------------------------------------------------------- /verl/trainer/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/main_eval.py -------------------------------------------------------------------------------- /verl/trainer/main_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/main_generation.py -------------------------------------------------------------------------------- /verl/trainer/main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/main_ppo.py -------------------------------------------------------------------------------- /verl/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /verl/trainer/ppo/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/ppo/core_algos.py -------------------------------------------------------------------------------- /verl/trainer/ppo/metric_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/ppo/metric_utils.py -------------------------------------------------------------------------------- /verl/trainer/ppo/ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/ppo/ray_trainer.py -------------------------------------------------------------------------------- /verl/trainer/ppo/reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/ppo/reward.py -------------------------------------------------------------------------------- /verl/trainer/runtime_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/trainer/runtime_env.yaml -------------------------------------------------------------------------------- /verl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/__init__.py -------------------------------------------------------------------------------- /verl/utils/activation_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/activation_offload.py -------------------------------------------------------------------------------- /verl/utils/api_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/api_config.py -------------------------------------------------------------------------------- /verl/utils/checkpoint/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/checkpoint/__init__.py -------------------------------------------------------------------------------- /verl/utils/checkpoint/checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/checkpoint/checkpoint_manager.py -------------------------------------------------------------------------------- /verl/utils/checkpoint/fsdp_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/checkpoint/fsdp_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/utils/checkpoint/megatron_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/checkpoint/megatron_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/config.py -------------------------------------------------------------------------------- /verl/utils/dataset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/dataset/README.md -------------------------------------------------------------------------------- /verl/utils/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/dataset/__init__.py -------------------------------------------------------------------------------- /verl/utils/dataset/multiturn_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/dataset/multiturn_sft_dataset.py -------------------------------------------------------------------------------- /verl/utils/dataset/rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/dataset/rl_dataset.py -------------------------------------------------------------------------------- /verl/utils/dataset/rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/dataset/rm_dataset.py -------------------------------------------------------------------------------- /verl/utils/dataset/sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/dataset/sft_dataset.py -------------------------------------------------------------------------------- /verl/utils/dataset/vision_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/dataset/vision_utils.py -------------------------------------------------------------------------------- /verl/utils/debug/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/debug/__init__.py -------------------------------------------------------------------------------- /verl/utils/debug/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/debug/metrics.py -------------------------------------------------------------------------------- /verl/utils/debug/performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/debug/performance.py -------------------------------------------------------------------------------- /verl/utils/debug/trajectory_tracker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/debug/trajectory_tracker.py -------------------------------------------------------------------------------- /verl/utils/device.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/device.py -------------------------------------------------------------------------------- /verl/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/distributed.py -------------------------------------------------------------------------------- /verl/utils/experimental/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/experimental/__init__.py -------------------------------------------------------------------------------- /verl/utils/experimental/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/experimental/torch_functional.py -------------------------------------------------------------------------------- /verl/utils/flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/flops_counter.py -------------------------------------------------------------------------------- /verl/utils/fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/fs.py -------------------------------------------------------------------------------- /verl/utils/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/fsdp_utils.py -------------------------------------------------------------------------------- /verl/utils/hdfs_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/hdfs_io.py -------------------------------------------------------------------------------- /verl/utils/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/import_utils.py -------------------------------------------------------------------------------- /verl/utils/kernel/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/kernel/__init__.py -------------------------------------------------------------------------------- /verl/utils/kernel/kernels.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/kernel/kernels.py -------------------------------------------------------------------------------- /verl/utils/kernel/linear_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/kernel/linear_cross_entropy.py -------------------------------------------------------------------------------- /verl/utils/logger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/logger/__init__.py -------------------------------------------------------------------------------- /verl/utils/logger/aggregate_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/logger/aggregate_logger.py -------------------------------------------------------------------------------- /verl/utils/logging_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/logging_utils.py -------------------------------------------------------------------------------- /verl/utils/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/megatron/__init__.py -------------------------------------------------------------------------------- /verl/utils/megatron/dist_checkpointing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/megatron/dist_checkpointing.py -------------------------------------------------------------------------------- /verl/utils/megatron/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/megatron/memory.py -------------------------------------------------------------------------------- /verl/utils/megatron/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/megatron/optimizer.py -------------------------------------------------------------------------------- /verl/utils/megatron/pipeline_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/megatron/pipeline_parallel.py -------------------------------------------------------------------------------- /verl/utils/megatron/sequence_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/megatron/sequence_parallel.py -------------------------------------------------------------------------------- /verl/utils/megatron/tensor_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/megatron/tensor_parallel.py -------------------------------------------------------------------------------- /verl/utils/megatron_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/megatron_utils.py -------------------------------------------------------------------------------- /verl/utils/memory_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/memory_buffer.py -------------------------------------------------------------------------------- /verl/utils/memory_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/memory_utils.py -------------------------------------------------------------------------------- /verl/utils/metric/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/metric/__init__.py -------------------------------------------------------------------------------- /verl/utils/metric/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/metric/utils.py -------------------------------------------------------------------------------- /verl/utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/model.py -------------------------------------------------------------------------------- /verl/utils/net_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/net_utils.py -------------------------------------------------------------------------------- /verl/utils/profiler/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/profiler/__init__.py -------------------------------------------------------------------------------- /verl/utils/profiler/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/profiler/config.py -------------------------------------------------------------------------------- /verl/utils/profiler/empty_annotations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/profiler/empty_annotations.py -------------------------------------------------------------------------------- /verl/utils/profiler/mstx_profile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/profiler/mstx_profile.py -------------------------------------------------------------------------------- /verl/utils/profiler/nvtx_profile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/profiler/nvtx_profile.py -------------------------------------------------------------------------------- /verl/utils/profiler/performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/profiler/performance.py -------------------------------------------------------------------------------- /verl/utils/profiler/profile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/profiler/profile.py -------------------------------------------------------------------------------- /verl/utils/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/py_functional.py -------------------------------------------------------------------------------- /verl/utils/ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/ray_utils.py -------------------------------------------------------------------------------- /verl/utils/rendezvous/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/rendezvous/__init__.py -------------------------------------------------------------------------------- /verl/utils/rendezvous/ray_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/rendezvous/ray_backend.py -------------------------------------------------------------------------------- /verl/utils/reward_score/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/__init__.py -------------------------------------------------------------------------------- /verl/utils/reward_score/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/geo3k.py -------------------------------------------------------------------------------- /verl/utils/reward_score/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/gsm8k.py -------------------------------------------------------------------------------- /verl/utils/reward_score/math_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/math_batch.py -------------------------------------------------------------------------------- /verl/utils/reward_score/math_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/math_dapo.py -------------------------------------------------------------------------------- /verl/utils/reward_score/math_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/math_utils.py -------------------------------------------------------------------------------- /verl/utils/reward_score/math_verify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/math_verify.py -------------------------------------------------------------------------------- /verl/utils/reward_score/prime_code/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/prime_code/README.md -------------------------------------------------------------------------------- /verl/utils/reward_score/prime_code/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/prime_code/__init__.py -------------------------------------------------------------------------------- /verl/utils/reward_score/prime_code/testing_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/prime_code/testing_util.py -------------------------------------------------------------------------------- /verl/utils/reward_score/prime_code/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/prime_code/utils.py -------------------------------------------------------------------------------- /verl/utils/reward_score/prime_math/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/prime_math/__init__.py -------------------------------------------------------------------------------- /verl/utils/reward_score/prime_math/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/prime_math/grader.py -------------------------------------------------------------------------------- /verl/utils/reward_score/prime_math/math_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/prime_math/math_normalize.py -------------------------------------------------------------------------------- /verl/utils/reward_score/prompt_gen_batch_sglang_v4_fast_f1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/prompt_gen_batch_sglang_v4_fast_f1.py -------------------------------------------------------------------------------- /verl/utils/reward_score/sandbox_fusion/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/sandbox_fusion/__init__.py -------------------------------------------------------------------------------- /verl/utils/reward_score/sandbox_fusion/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/sandbox_fusion/utils.py -------------------------------------------------------------------------------- /verl/utils/reward_score/search_r1_like_qa_em.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/reward_score/search_r1_like_qa_em.py -------------------------------------------------------------------------------- /verl/utils/rollout_skip.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/rollout_skip.py -------------------------------------------------------------------------------- /verl/utils/rollout_trace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/rollout_trace.py -------------------------------------------------------------------------------- /verl/utils/seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/seqlen_balancing.py -------------------------------------------------------------------------------- /verl/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/tokenizer.py -------------------------------------------------------------------------------- /verl/utils/torch_dtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/torch_dtypes.py -------------------------------------------------------------------------------- /verl/utils/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/torch_functional.py -------------------------------------------------------------------------------- /verl/utils/tracking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/tracking.py -------------------------------------------------------------------------------- /verl/utils/transformers_compat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/transformers_compat.py -------------------------------------------------------------------------------- /verl/utils/ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/ulysses.py -------------------------------------------------------------------------------- /verl/utils/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/vllm/__init__.py -------------------------------------------------------------------------------- /verl/utils/vllm/patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/vllm/patch.py -------------------------------------------------------------------------------- /verl/utils/vllm/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/utils/vllm/utils.py -------------------------------------------------------------------------------- /verl/version/version: -------------------------------------------------------------------------------- 1 | 0.5.0.dev 2 | -------------------------------------------------------------------------------- /verl/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/__init__.py -------------------------------------------------------------------------------- /verl/workers/actor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/actor/__init__.py -------------------------------------------------------------------------------- /verl/workers/actor/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/actor/base.py -------------------------------------------------------------------------------- /verl/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /verl/workers/actor/megatron_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/actor/megatron_actor.py -------------------------------------------------------------------------------- /verl/workers/config/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/config/__init__.py -------------------------------------------------------------------------------- /verl/workers/config/actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/config/actor.py -------------------------------------------------------------------------------- /verl/workers/config/critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/config/critic.py -------------------------------------------------------------------------------- /verl/workers/config/engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/config/engine.py -------------------------------------------------------------------------------- /verl/workers/config/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/config/optimizer.py -------------------------------------------------------------------------------- /verl/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/critic/__init__.py -------------------------------------------------------------------------------- /verl/workers/critic/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/critic/base.py -------------------------------------------------------------------------------- /verl/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /verl/workers/critic/megatron_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/critic/megatron_critic.py -------------------------------------------------------------------------------- /verl/workers/engine/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/engine/__init__.py -------------------------------------------------------------------------------- /verl/workers/engine/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/engine/base.py -------------------------------------------------------------------------------- /verl/workers/engine/fsdp/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/engine/fsdp/__init__.py -------------------------------------------------------------------------------- /verl/workers/engine/fsdp/engine_impl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/engine/fsdp/engine_impl.py -------------------------------------------------------------------------------- /verl/workers/engine/fsdp/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/engine/fsdp/utils.py -------------------------------------------------------------------------------- /verl/workers/engine/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/engine/megatron/__init__.py -------------------------------------------------------------------------------- /verl/workers/engine/megatron/engine_impl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/engine/megatron/engine_impl.py -------------------------------------------------------------------------------- /verl/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/fsdp_workers.py -------------------------------------------------------------------------------- /verl/workers/megatron_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/megatron_workers.py -------------------------------------------------------------------------------- /verl/workers/reward_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_manager/__init__.py -------------------------------------------------------------------------------- /verl/workers/reward_manager/abstract.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_manager/abstract.py -------------------------------------------------------------------------------- /verl/workers/reward_manager/batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_manager/batch.py -------------------------------------------------------------------------------- /verl/workers/reward_manager/dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_manager/dapo.py -------------------------------------------------------------------------------- /verl/workers/reward_manager/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_manager/naive.py -------------------------------------------------------------------------------- /verl/workers/reward_manager/prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_manager/prime.py -------------------------------------------------------------------------------- /verl/workers/reward_manager/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_manager/registry.py -------------------------------------------------------------------------------- /verl/workers/reward_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_model/__init__.py -------------------------------------------------------------------------------- /verl/workers/reward_model/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_model/base.py -------------------------------------------------------------------------------- /verl/workers/reward_model/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_model/megatron/__init__.py -------------------------------------------------------------------------------- /verl/workers/reward_model/megatron/reward_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/reward_model/megatron/reward_model.py -------------------------------------------------------------------------------- /verl/workers/roles/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/roles/__init__.py -------------------------------------------------------------------------------- /verl/workers/roles/actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/roles/actor.py -------------------------------------------------------------------------------- /verl/workers/roles/critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/roles/critic.py -------------------------------------------------------------------------------- /verl/workers/rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/__init__.py -------------------------------------------------------------------------------- /verl/workers/rollout/async_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/async_server.py -------------------------------------------------------------------------------- /verl/workers/rollout/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/base.py -------------------------------------------------------------------------------- /verl/workers/rollout/hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/hf_rollout.py -------------------------------------------------------------------------------- /verl/workers/rollout/naive/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/naive/__init__.py -------------------------------------------------------------------------------- /verl/workers/rollout/naive/naive_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/naive/naive_rollout.py -------------------------------------------------------------------------------- /verl/workers/rollout/schemas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/schemas.py -------------------------------------------------------------------------------- /verl/workers/rollout/sglang_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/sglang_rollout/__init__.py -------------------------------------------------------------------------------- /verl/workers/rollout/sglang_rollout/async_sglang_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/sglang_rollout/async_sglang_server.py -------------------------------------------------------------------------------- /verl/workers/rollout/sglang_rollout/sglang_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/sglang_rollout/sglang_rollout.py -------------------------------------------------------------------------------- /verl/workers/rollout/sglang_rollout/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/sglang_rollout/utils.py -------------------------------------------------------------------------------- /verl/workers/rollout/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/tokenizer.py -------------------------------------------------------------------------------- /verl/workers/rollout/vllm_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/vllm_rollout/__init__.py -------------------------------------------------------------------------------- /verl/workers/rollout/vllm_rollout/vllm_async_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/vllm_rollout/vllm_async_server.py -------------------------------------------------------------------------------- /verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/sharding_manager/__init__.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/fsdp_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/sharding_manager/fsdp_sglang.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/fsdp_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/sharding_manager/fsdp_ulysses.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/sharding_manager/fsdp_vllm.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/megatron_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/sharding_manager/megatron_sglang.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/megatron_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl/workers/sharding_manager/megatron_vllm.py -------------------------------------------------------------------------------- /verl_readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/verl_readme.md -------------------------------------------------------------------------------- /view_preprocessed_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/millix19/promptmii/HEAD/view_preprocessed_data.py --------------------------------------------------------------------------------